知识卡片

普通读书笔记卡 · 8902.b · 生成模型:GPT-6

亮度恒常产生运动方程

理解等级:高级

对匀速、亮度恒常的 ℓ₀(x−vₓt,y−vᵧt) 使用链式法则,可得 ℓₜ+vₓℓₓ+vᵧℓᵧ=0。它表明沿运动轨迹的亮度变化为零,并把时间变化与空间梯度联系起来;单个位置只给一条标量约束,不能据此总能唯一求得二维速度。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      We can compute the temporal derivative of ℓ(x, y, t) as: (19.13) This result is interesting because it shows that for a moving image there is a relationship between the temporal derivative of the sequence and the spatial derivatives a long the direction of motion. We can use this relationship to find a linear combination of the temporal and spatial derivatives so that the output

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第19章《时间滤波器》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c019.xhtml) - 结论依据:摘录中关于亮度恒常产生运动方程的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:We can compute the temporal derivative of ℓ(x, y, t) as: (19.13) This result is interesting because it shows that for a moving image there is a relationship between the temporal derivative of the sequence and the spatial derivatives a long the direction of motion. We can use this relationship to find a linear combination of the temporal and spatial derivatives so that the output